config-reference.md Codex Docs, 2026-02-24 00:33 UTC → 2026-04-17 00:44 UTC

6 6 

7User-level configuration lives in `~/.codex/config.toml`. You can also add project-scoped overrides in `.codex/config.toml` files. Codex loads project-scoped config files only when you trust the project.7User-level configuration lives in `~/.codex/config.toml`. You can also add project-scoped overrides in `.codex/config.toml` files. Codex loads project-scoped config files only when you trust the project.

8 8 

9For sandbox and approval keys (`approval_policy`, `sandbox_mode`, and `sandbox_workspace_write.*`), pair this reference with [Sandbox and approvals](https://developers.openai.com/codex/security#sandbox-and-approvals), [Protected paths in writable roots](https://developers.openai.com/codex/security#protected-paths-in-writable-roots), and [Network access](https://developers.openai.com/codex/security#network-access).9For sandbox and approval keys (`approval_policy`, `sandbox_mode`, and `sandbox_workspace_write.*`), pair this reference with [Sandbox and approvals](https://developers.openai.com/codex/agent-approvals-security#sandbox-and-approvals), [Protected paths in writable roots](https://developers.openai.com/codex/agent-approvals-security#protected-paths-in-writable-roots), and [Network access](https://developers.openai.com/codex/agent-approvals-security#network-access).

10 10 

11| Key | Type / Values | Details |11| Key | Type / Values | Details |

12| --- | --- | --- |12| --- | --- | --- |

13| `agents.<name>.config_file` | `string (path)` | Path to a TOML config layer for that role; relative paths resolve from the config file that declares the role. |13| `agents.<name>.config_file` | `string (path)` | Path to a TOML config layer for that role; relative paths resolve from the config file that declares the role. |

14| `agents.<name>.description` | `string` | Role guidance shown to Codex when choosing and spawning that agent type. |14| `agents.<name>.description` | `string` | Role guidance shown to Codex when choosing and spawning that agent type. |

15| `agents.<name>.nickname_candidates` | `array<string>` | Optional pool of display nicknames for spawned agents in that role. |

16| `agents.job_max_runtime_seconds` | `number` | Default per-worker timeout for `spawn_agents_on_csv` jobs. When unset, the tool falls back to 1800 seconds per worker. |

15| `agents.max_depth` | `number` | Maximum nesting depth allowed for spawned agent threads (root sessions start at depth 0; default: 1). |17| `agents.max_depth` | `number` | Maximum nesting depth allowed for spawned agent threads (root sessions start at depth 0; default: 1). |

16| `agents.max_threads` | `number` | Maximum number of agent threads that can be open concurrently. |18| `agents.max_threads` | `number` | Maximum number of agent threads that can be open concurrently. Defaults to `6` when unset. |

17| `allow_login_shell` | `boolean` | Allow shell-based tools to use login-shell semantics. Defaults to `true`; when `false`, `login = true` requests are rejected and omitted `login` defaults to non-login shells. |19| `allow_login_shell` | `boolean` | Allow shell-based tools to use login-shell semantics. Defaults to `true`; when `false`, `login = true` requests are rejected and omitted `login` defaults to non-login shells. |

18| `approval_policy` | `untrusted | on-request | never | { reject = { sandbox_approval = bool, rules = bool, mcp_elicitations = bool } }` | Controls when Codex pauses for approval before executing commands. You can also use `approval_policy = { reject = { ... } }` to auto-reject specific prompt categories while keeping other prompts interactive. `on-failure` is deprecated; use `on-request` for interactive runs or `never` for non-interactive runs. |20| `analytics.enabled` | `boolean` | Enable or disable analytics for this machine/profile. When unset, the client default applies. |

19| `approval_policy.reject.mcp_elicitations` | `boolean` | When `true`, MCP elicitation prompts are auto-rejected instead of shown to the user. |21| `approval_policy` | `untrusted | on-request | never | { granular = { sandbox_approval = bool, rules = bool, mcp_elicitations = bool, request_permissions = bool, skill_approval = bool } }` | Controls when Codex pauses for approval before executing commands. You can also use `approval_policy = { granular = { ... } }` to allow or auto-reject specific prompt categories while keeping other prompts interactive. `on-failure` is deprecated; use `on-request` for interactive runs or `never` for non-interactive runs. |

20| `approval_policy.reject.rules` | `boolean` | When `true`, approvals triggered by execpolicy `prompt` rules are auto-rejected. |22| `approval_policy.granular.mcp_elicitations` | `boolean` | When `true`, MCP elicitation prompts are allowed to surface instead of being auto-rejected. |

21| `approval_policy.reject.sandbox_approval` | `boolean` | When `true`, sandbox escalation approval prompts are auto-rejected. |23| `approval_policy.granular.request_permissions` | `boolean` | When `true`, prompts from the `request_permissions` tool are allowed to surface. |

24| `approval_policy.granular.rules` | `boolean` | When `true`, approvals triggered by execpolicy `prompt` rules are allowed to surface. |

25| `approval_policy.granular.sandbox_approval` | `boolean` | When `true`, sandbox escalation approval prompts are allowed to surface. |

26| `approval_policy.granular.skill_approval` | `boolean` | When `true`, skill-script approval prompts are allowed to surface. |

27| `approvals_reviewer` | `user | guardian_subagent` | Select who reviews eligible approval prompts. Defaults to `user`; `guardian_subagent` routes supported reviews through the Guardian reviewer subagent. |

22| `apps._default.destructive_enabled` | `boolean` | Default allow/deny for app tools with `destructive_hint = true`. |28| `apps._default.destructive_enabled` | `boolean` | Default allow/deny for app tools with `destructive_hint = true`. |

23| `apps._default.enabled` | `boolean` | Default app enabled state for all apps unless overridden per app. |29| `apps._default.enabled` | `boolean` | Default app enabled state for all apps unless overridden per app. |

24| `apps._default.open_world_enabled` | `boolean` | Default allow/deny for app tools with `open_world_hint = true`. |30| `apps._default.open_world_enabled` | `boolean` | Default allow/deny for app tools with `open_world_hint = true`. |

33| `chatgpt_base_url` | `string` | Override the base URL used during the ChatGPT login flow. |39| `chatgpt_base_url` | `string` | Override the base URL used during the ChatGPT login flow. |

34| `check_for_update_on_startup` | `boolean` | Check for Codex updates on startup (set to false only when updates are centrally managed). |40| `check_for_update_on_startup` | `boolean` | Check for Codex updates on startup (set to false only when updates are centrally managed). |

35| `cli_auth_credentials_store` | `file | keyring | auto` | Control where the CLI stores cached credentials (file-based auth.json vs OS keychain). |41| `cli_auth_credentials_store` | `file | keyring | auto` | Control where the CLI stores cached credentials (file-based auth.json vs OS keychain). |

42| `commit_attribution` | `string` | Override the commit co-author trailer text. Set an empty string to disable automatic attribution. |

36| `compact_prompt` | `string` | Inline override for the history compaction prompt. |43| `compact_prompt` | `string` | Inline override for the history compaction prompt. |

44| `default_permissions` | `string` | Name of the default permissions profile to apply to sandboxed tool calls. |

37| `developer_instructions` | `string` | Additional developer instructions injected into the session (optional). |45| `developer_instructions` | `string` | Additional developer instructions injected into the session (optional). |

38| `disable_paste_burst` | `boolean` | Disable burst-paste detection in the TUI. |46| `disable_paste_burst` | `boolean` | Disable burst-paste detection in the TUI. |

39| `experimental_compact_prompt_file` | `string (path)` | Load the compaction prompt override from a file (experimental). |47| `experimental_compact_prompt_file` | `string (path)` | Load the compaction prompt override from a file (experimental). |

40| `experimental_use_freeform_apply_patch` | `boolean` | Legacy name for enabling freeform apply\_patch; prefer `[features].apply_patch_freeform` or `codex --enable apply_patch_freeform`. |

41| `experimental_use_unified_exec_tool` | `boolean` | Legacy name for enabling unified exec; prefer `[features].unified_exec` or `codex --enable unified_exec`. |48| `experimental_use_unified_exec_tool` | `boolean` | Legacy name for enabling unified exec; prefer `[features].unified_exec` or `codex --enable unified_exec`. |

42| `features.apply_patch_freeform` | `boolean` | Expose the freeform `apply_patch` tool (experimental). |

43| `features.apps` | `boolean` | Enable ChatGPT Apps/connectors support (experimental). |49| `features.apps` | `boolean` | Enable ChatGPT Apps/connectors support (experimental). |

44| `features.apps_mcp_gateway` | `boolean` | Route Apps MCP calls through the OpenAI connectors MCP gateway (`https://api.openai.com/v1/connectors/mcp/`) instead of legacy routing (experimental). |50| `features.codex_hooks` | `boolean` | Enable lifecycle hooks loaded from `hooks.json` (under development; off by default). |

45| `features.child_agents_md` | `boolean` | Append AGENTS.md scope/precedence guidance even when no AGENTS.md is present (experimental). |51| `features.enable_request_compression` | `boolean` | Compress streaming request bodies with zstd when supported (stable; on by default). |

46| `features.collaboration_modes` | `boolean` | Enable collaboration modes such as plan mode (stable; on by default). |52| `features.fast_mode` | `boolean` | Enable Fast mode selection and the `service_tier = "fast"` path (stable; on by default). |

47| `features.elevated_windows_sandbox` | `boolean` | Enable the elevated Windows sandbox pipeline (experimental). |53| `features.memories` | `boolean` | Enable [Memories](https://developers.openai.com/codex/memories) (off by default). |

48| `features.experimental_windows_sandbox` | `boolean` | Run the Windows restricted-token sandbox (experimental). |54| `features.multi_agent` | `boolean` | Enable multi-agent collaboration tools (`spawn_agent`, `send_input`, `resume_agent`, `wait_agent`, and `close_agent`) (stable; on by default). |

49| `features.multi_agent` | `boolean` | Enable multi-agent collaboration tools (`spawn\_agent`, `send\_input`, `resume\_agent`, `wait`, and `close\_agent`) (experimental; off by default). |

50| `features.personality` | `boolean` | Enable personality selection controls (stable; on by default). |55| `features.personality` | `boolean` | Enable personality selection controls (stable; on by default). |

51| `features.powershell_utf8` | `boolean` | Force PowerShell UTF-8 output (defaults to true). |56| `features.prevent_idle_sleep` | `boolean` | Prevent the machine from sleeping while a turn is actively running (experimental; off by default). |

52| `features.remote_models` | `boolean` | Refresh remote model list before showing readiness (experimental). |57| `features.shell_snapshot` | `boolean` | Snapshot shell environment to speed up repeated commands (stable; on by default). |

53| `features.request_rule` | `boolean` | Enable Smart approvals (`prefix_rule` suggestions on escalation requests; stable; on by default). |

54| `features.runtime_metrics` | `boolean` | Show runtime metrics summary in TUI turn separators (experimental). |

55| `features.search_tool` | `boolean` | Enable `search_tool_bm25` for Apps tool discovery before invoking app MCP tools (experimental). |

56| `features.shell_snapshot` | `boolean` | Snapshot shell environment to speed up repeated commands (beta). |

57| `features.shell_tool` | `boolean` | Enable the default `shell` tool for running commands (stable; on by default). |58| `features.shell_tool` | `boolean` | Enable the default `shell` tool for running commands (stable; on by default). |

58| `features.unified_exec` | `boolean` | Use the unified PTY-backed exec tool (beta). |59| `features.skill_mcp_dependency_install` | `boolean` | Allow prompting and installing missing MCP dependencies for skills (stable; on by default). |

59| `features.use_linux_sandbox_bwrap` | `boolean` | Use the bubblewrap-based Linux sandbox pipeline (experimental; off by default). |60| `features.smart_approvals` | `boolean` | Route eligible approval requests through the guardian reviewer subagent (experimental; off by default). |

61| `features.undo` | `boolean` | Enable undo support (stable; off by default). |

62| `features.unified_exec` | `boolean` | Use the unified PTY-backed exec tool (stable; enabled by default except on Windows). |

60| `features.web_search` | `boolean` | Deprecated legacy toggle; prefer the top-level `web_search` setting. |63| `features.web_search` | `boolean` | Deprecated legacy toggle; prefer the top-level `web_search` setting. |

61| `features.web_search_cached` | `boolean` | Deprecated legacy toggle. When `web_search` is unset, true maps to `web_search = "cached"`. |64| `features.web_search_cached` | `boolean` | Deprecated legacy toggle. When `web_search` is unset, true maps to `web_search = "cached"`. |

62| `features.web_search_request` | `boolean` | Deprecated legacy toggle. When `web_search` is unset, true maps to `web_search = "live"`. |65| `features.web_search_request` | `boolean` | Deprecated legacy toggle. When `web_search` is unset, true maps to `web_search = "live"`. |

67| `hide_agent_reasoning` | `boolean` | Suppress reasoning events in both the TUI and `codex exec` output. |70| `hide_agent_reasoning` | `boolean` | Suppress reasoning events in both the TUI and `codex exec` output. |

68| `history.max_bytes` | `number` | If set, caps the history file size in bytes by dropping oldest entries. |71| `history.max_bytes` | `number` | If set, caps the history file size in bytes by dropping oldest entries. |

69| `history.persistence` | `save-all | none` | Control whether Codex saves session transcripts to history.jsonl. |72| `history.persistence` | `save-all | none` | Control whether Codex saves session transcripts to history.jsonl. |

70| `include_apply_patch_tool` | `boolean` | Legacy name for enabling freeform apply\_patch; prefer `[features].apply_patch_freeform`. |

71| `instructions` | `string` | Reserved for future use; prefer `model_instructions_file` or `AGENTS.md`. |73| `instructions` | `string` | Reserved for future use; prefer `model_instructions_file` or `AGENTS.md`. |

72| `log_dir` | `string (path)` | Directory where Codex writes log files (for example `codex-tui.log`); defaults to `$CODEX_HOME/log`. |74| `log_dir` | `string (path)` | Directory where Codex writes log files (for example `codex-tui.log`); defaults to `$CODEX_HOME/log`. |

73| `mcp_oauth_callback_port` | `integer` | Optional fixed port for the local HTTP callback server used during MCP OAuth login. When unset, Codex binds to an ephemeral port chosen by the OS. |75| `mcp_oauth_callback_port` | `integer` | Optional fixed port for the local HTTP callback server used during MCP OAuth login. When unset, Codex binds to an ephemeral port chosen by the OS. |

84| `mcp_servers.<id>.env_http_headers` | `map<string,string>` | HTTP headers populated from environment variables for an MCP HTTP server. |86| `mcp_servers.<id>.env_http_headers` | `map<string,string>` | HTTP headers populated from environment variables for an MCP HTTP server. |

85| `mcp_servers.<id>.env_vars` | `array<string>` | Additional environment variables to whitelist for an MCP stdio server. |87| `mcp_servers.<id>.env_vars` | `array<string>` | Additional environment variables to whitelist for an MCP stdio server. |

86| `mcp_servers.<id>.http_headers` | `map<string,string>` | Static HTTP headers included with each MCP HTTP request. |88| `mcp_servers.<id>.http_headers` | `map<string,string>` | Static HTTP headers included with each MCP HTTP request. |

89| `mcp_servers.<id>.oauth_resource` | `string` | Optional RFC 8707 OAuth resource parameter to include during MCP login. |

87| `mcp_servers.<id>.required` | `boolean` | When true, fail startup/resume if this enabled MCP server cannot initialize. |90| `mcp_servers.<id>.required` | `boolean` | When true, fail startup/resume if this enabled MCP server cannot initialize. |

91| `mcp_servers.<id>.scopes` | `array<string>` | OAuth scopes to request when authenticating to that MCP server. |

88| `mcp_servers.<id>.startup_timeout_ms` | `number` | Alias for `startup_timeout_sec` in milliseconds. |92| `mcp_servers.<id>.startup_timeout_ms` | `number` | Alias for `startup_timeout_sec` in milliseconds. |

89| `mcp_servers.<id>.startup_timeout_sec` | `number` | Override the default 10s startup timeout for an MCP server. |93| `mcp_servers.<id>.startup_timeout_sec` | `number` | Override the default 10s startup timeout for an MCP server. |

90| `mcp_servers.<id>.tool_timeout_sec` | `number` | Override the default 60s per-tool timeout for an MCP server. |94| `mcp_servers.<id>.tool_timeout_sec` | `number` | Override the default 60s per-tool timeout for an MCP server. |

91| `mcp_servers.<id>.url` | `string` | Endpoint for an MCP streamable HTTP server. |95| `mcp_servers.<id>.url` | `string` | Endpoint for an MCP streamable HTTP server. |

92| `model` | `string` | Model to use (e.g., `gpt-5-codex`). |96| `memories.consolidation_model` | `string` | Optional model override for global memory consolidation. |

97| `memories.extract_model` | `string` | Optional model override for per-thread memory extraction. |

98| `memories.generate_memories` | `boolean` | When `false`, newly created threads are not stored as memory-generation inputs. Defaults to `true`. |

99| `memories.max_raw_memories_for_consolidation` | `number` | Maximum recent raw memories retained for global consolidation. Defaults to `256` and is capped at `4096`. |

100| `memories.max_rollout_age_days` | `number` | Maximum age of threads considered for memory generation. Defaults to `30` and is clamped to `0`-`90`. |

101| `memories.max_rollouts_per_startup` | `number` | Maximum rollout candidates processed per startup pass. Defaults to `16` and is capped at `128`. |

102| `memories.max_unused_days` | `number` | Maximum days since a memory was last used before it becomes ineligible for consolidation. Defaults to `30` and is clamped to `0`-`365`. |

103| `memories.min_rollout_idle_hours` | `number` | Minimum idle time before a thread is considered for memory generation. Defaults to `6` and is clamped to `1`-`48`. |

104| `memories.no_memories_if_mcp_or_web_search` | `boolean` | When `true`, threads that use MCP tool calls or web search are kept out of memory generation. Defaults to `false`. |

105| `memories.use_memories` | `boolean` | When `false`, Codex skips injecting existing memories into future sessions. Defaults to `true`. |

106| `model` | `string` | Model to use (e.g., `gpt-5.4`). |

93| `model_auto_compact_token_limit` | `number` | Token threshold that triggers automatic history compaction (unset uses model defaults). |107| `model_auto_compact_token_limit` | `number` | Token threshold that triggers automatic history compaction (unset uses model defaults). |

94| `model_catalog_json` | `string (path)` | Optional path to a JSON model catalog loaded on startup. Profile-level `profiles.<name>.model_catalog_json` can override this per profile. |108| `model_catalog_json` | `string (path)` | Optional path to a JSON model catalog loaded on startup. Profile-level `profiles.<name>.model_catalog_json` can override this per profile. |

95| `model_context_window` | `number` | Context window tokens available to the active model. |109| `model_context_window` | `number` | Context window tokens available to the active model. |

96| `model_instructions_file` | `string (path)` | Replacement for built-in instructions instead of `AGENTS.md`. |110| `model_instructions_file` | `string (path)` | Replacement for built-in instructions instead of `AGENTS.md`. |

97| `model_provider` | `string` | Provider id from `model_providers` (default: `openai`). |111| `model_provider` | `string` | Provider id from `model_providers` (default: `openai`). |

112| `model_providers.<id>` | `table` | Custom provider definition. Built-in provider IDs (`openai`, `ollama`, and `lmstudio`) are reserved and cannot be overridden. |

113| `model_providers.<id>.auth` | `table` | Command-backed bearer token configuration for a custom provider. Do not combine with `env_key`, `experimental_bearer_token`, or `requires_openai_auth`. |

114| `model_providers.<id>.auth.args` | `array<string>` | Arguments passed to the token command. |

115| `model_providers.<id>.auth.command` | `string` | Command to run when Codex needs a bearer token. The command must print the token to stdout. |

116| `model_providers.<id>.auth.cwd` | `string (path)` | Working directory for the token command. |

117| `model_providers.<id>.auth.refresh_interval_ms` | `number` | How often Codex proactively refreshes the token in milliseconds (default: 300000). Set to `0` to refresh only after an authentication retry. |

118| `model_providers.<id>.auth.timeout_ms` | `number` | Maximum token command runtime in milliseconds (default: 5000). |

98| `model_providers.<id>.base_url` | `string` | API base URL for the model provider. |119| `model_providers.<id>.base_url` | `string` | API base URL for the model provider. |

99| `model_providers.<id>.env_http_headers` | `map<string,string>` | HTTP headers populated from environment variables when present. |120| `model_providers.<id>.env_http_headers` | `map<string,string>` | HTTP headers populated from environment variables when present. |

100| `model_providers.<id>.env_key` | `string` | Environment variable supplying the provider API key. |121| `model_providers.<id>.env_key` | `string` | Environment variable supplying the provider API key. |

107| `model_providers.<id>.requires_openai_auth` | `boolean` | The provider uses OpenAI authentication (defaults to false). |128| `model_providers.<id>.requires_openai_auth` | `boolean` | The provider uses OpenAI authentication (defaults to false). |

108| `model_providers.<id>.stream_idle_timeout_ms` | `number` | Idle timeout for SSE streams in milliseconds (default: 300000). |129| `model_providers.<id>.stream_idle_timeout_ms` | `number` | Idle timeout for SSE streams in milliseconds (default: 300000). |

109| `model_providers.<id>.stream_max_retries` | `number` | Retry count for SSE streaming interruptions (default: 5). |130| `model_providers.<id>.stream_max_retries` | `number` | Retry count for SSE streaming interruptions (default: 5). |

110| `model_providers.<id>.wire_api` | `chat | responses` | Protocol used by the provider (defaults to `chat` if omitted). |131| `model_providers.<id>.supports_websockets` | `boolean` | Whether that provider supports the Responses API WebSocket transport. |

132| `model_providers.<id>.wire_api` | `responses` | Protocol used by the provider. `responses` is the only supported value, and it is the default when omitted. |

111| `model_reasoning_effort` | `minimal | low | medium | high | xhigh` | Adjust reasoning effort for supported models (Responses API only; `xhigh` is model-dependent). |133| `model_reasoning_effort` | `minimal | low | medium | high | xhigh` | Adjust reasoning effort for supported models (Responses API only; `xhigh` is model-dependent). |

112| `model_reasoning_summary` | `auto | concise | detailed | none` | Select reasoning summary detail or disable summaries entirely. |134| `model_reasoning_summary` | `auto | concise | detailed | none` | Select reasoning summary detail or disable summaries entirely. |

113| `model_supports_reasoning_summaries` | `boolean` | Force Codex to send or not send reasoning metadata. |135| `model_supports_reasoning_summaries` | `boolean` | Force Codex to send or not send reasoning metadata. |

114| `model_verbosity` | `low | medium | high` | Control GPT-5 Responses API verbosity (defaults to `medium`). |136| `model_verbosity` | `low | medium | high` | Optional GPT-5 Responses API verbosity override; when unset, the selected model/preset default is used. |

115| `notice.hide_full_access_warning` | `boolean` | Track acknowledgement of the full access warning prompt. |137| `notice.hide_full_access_warning` | `boolean` | Track acknowledgement of the full access warning prompt. |

116| `notice.hide_gpt-5.1-codex-max_migration_prompt` | `boolean` | Track acknowledgement of the gpt-5.1-codex-max migration prompt. |138| `notice.hide_gpt-5.1-codex-max_migration_prompt` | `boolean` | Track acknowledgement of the gpt-5.1-codex-max migration prompt. |

117| `notice.hide_gpt5_1_migration_prompt` | `boolean` | Track acknowledgement of the GPT-5.1 migration prompt. |139| `notice.hide_gpt5_1_migration_prompt` | `boolean` | Track acknowledgement of the GPT-5.1 migration prompt. |

119| `notice.hide_world_writable_warning` | `boolean` | Track acknowledgement of the Windows world-writable directories warning. |141| `notice.hide_world_writable_warning` | `boolean` | Track acknowledgement of the Windows world-writable directories warning. |

120| `notice.model_migrations` | `map<string,string>` | Track acknowledged model migrations as old->new mappings. |142| `notice.model_migrations` | `map<string,string>` | Track acknowledged model migrations as old->new mappings. |

121| `notify` | `array<string>` | Command invoked for notifications; receives a JSON payload from Codex. |143| `notify` | `array<string>` | Command invoked for notifications; receives a JSON payload from Codex. |

144| `openai_base_url` | `string` | Base URL override for the built-in `openai` model provider. |

122| `oss_provider` | `lmstudio | ollama` | Default local provider used when running with `--oss` (defaults to prompting if unset). |145| `oss_provider` | `lmstudio | ollama` | Default local provider used when running with `--oss` (defaults to prompting if unset). |

123| `otel.environment` | `string` | Environment tag applied to emitted OpenTelemetry events (default: `dev`). |146| `otel.environment` | `string` | Environment tag applied to emitted OpenTelemetry events (default: `dev`). |

124| `otel.exporter` | `none | otlp-http | otlp-grpc` | Select the OpenTelemetry exporter and provide any endpoint metadata. |147| `otel.exporter` | `none | otlp-http | otlp-grpc` | Select the OpenTelemetry exporter and provide any endpoint metadata. |

129| `otel.exporter.<id>.tls.client-certificate` | `string` | Client certificate path for OTEL exporter TLS. |152| `otel.exporter.<id>.tls.client-certificate` | `string` | Client certificate path for OTEL exporter TLS. |

130| `otel.exporter.<id>.tls.client-private-key` | `string` | Client private key path for OTEL exporter TLS. |153| `otel.exporter.<id>.tls.client-private-key` | `string` | Client private key path for OTEL exporter TLS. |

131| `otel.log_user_prompt` | `boolean` | Opt in to exporting raw user prompts with OpenTelemetry logs. |154| `otel.log_user_prompt` | `boolean` | Opt in to exporting raw user prompts with OpenTelemetry logs. |

155| `otel.metrics_exporter` | `none | statsig | otlp-http | otlp-grpc` | Select the OpenTelemetry metrics exporter (defaults to `statsig`). |

132| `otel.trace_exporter` | `none | otlp-http | otlp-grpc` | Select the OpenTelemetry trace exporter and provide any endpoint metadata. |156| `otel.trace_exporter` | `none | otlp-http | otlp-grpc` | Select the OpenTelemetry trace exporter and provide any endpoint metadata. |

133| `otel.trace_exporter.<id>.endpoint` | `string` | Trace exporter endpoint for OTEL logs. |157| `otel.trace_exporter.<id>.endpoint` | `string` | Trace exporter endpoint for OTEL logs. |

134| `otel.trace_exporter.<id>.headers` | `map<string,string>` | Static headers included with OTEL trace exporter requests. |158| `otel.trace_exporter.<id>.headers` | `map<string,string>` | Static headers included with OTEL trace exporter requests. |

136| `otel.trace_exporter.<id>.tls.ca-certificate` | `string` | CA certificate path for OTEL trace exporter TLS. |160| `otel.trace_exporter.<id>.tls.ca-certificate` | `string` | CA certificate path for OTEL trace exporter TLS. |

137| `otel.trace_exporter.<id>.tls.client-certificate` | `string` | Client certificate path for OTEL trace exporter TLS. |161| `otel.trace_exporter.<id>.tls.client-certificate` | `string` | Client certificate path for OTEL trace exporter TLS. |

138| `otel.trace_exporter.<id>.tls.client-private-key` | `string` | Client private key path for OTEL trace exporter TLS. |162| `otel.trace_exporter.<id>.tls.client-private-key` | `string` | Client private key path for OTEL trace exporter TLS. |

163| `permissions.<name>.filesystem` | `table` | Named filesystem permission profile. Each key is an absolute path or special token such as `:minimal` or `:project_roots`. |

164| `permissions.<name>.filesystem.":project_roots".<subpath>` | `"read" | "write" | "none"` | Scoped filesystem access relative to the detected project roots. Use `"."` for the root itself. |

165| `permissions.<name>.filesystem.<path>` | `"read" | "write" | "none" | table` | Grant direct access for a path or special token, or scope nested entries under that root. |

166| `permissions.<name>.network.allow_local_binding` | `boolean` | Permit local bind/listen operations through the managed proxy. |

167| `permissions.<name>.network.allow_upstream_proxy` | `boolean` | Allow the managed proxy to chain to another upstream proxy. |

168| `permissions.<name>.network.dangerously_allow_all_unix_sockets` | `boolean` | Allow the proxy to use arbitrary Unix sockets instead of the default restricted set. |

169| `permissions.<name>.network.dangerously_allow_non_loopback_proxy` | `boolean` | Permit non-loopback bind addresses for the managed proxy listener. |

170| `permissions.<name>.network.domains` | `map<string, allow | deny>` | Domain rules for the managed proxy. Use domain names or wildcard patterns as keys, with `allow` or `deny` values. |

171| `permissions.<name>.network.enable_socks5` | `boolean` | Expose a SOCKS5 listener when this permissions profile enables the managed network proxy. |

172| `permissions.<name>.network.enable_socks5_udp` | `boolean` | Allow UDP over the SOCKS5 listener when enabled. |

173| `permissions.<name>.network.enabled` | `boolean` | Enable network access for this named permissions profile. |

174| `permissions.<name>.network.mode` | `limited | full` | Network proxy mode used for subprocess traffic. |

175| `permissions.<name>.network.proxy_url` | `string` | HTTP proxy endpoint used when this permissions profile enables the managed network proxy. |

176| `permissions.<name>.network.socks_url` | `string` | SOCKS5 proxy endpoint used by this permissions profile. |

177| `permissions.<name>.network.unix_sockets` | `map<string, allow | none>` | Unix socket rules for the managed proxy. Use socket paths as keys, with `allow` or `none` values. |

139| `personality` | `none | friendly | pragmatic` | Default communication style for models that advertise `supportsPersonality`; can be overridden per thread/turn or via `/personality`. |178| `personality` | `none | friendly | pragmatic` | Default communication style for models that advertise `supportsPersonality`; can be overridden per thread/turn or via `/personality`. |

179| `plan_mode_reasoning_effort` | `none | minimal | low | medium | high | xhigh` | Plan-mode-specific reasoning override. When unset, Plan mode uses its built-in preset default. |

140| `profile` | `string` | Default profile applied at startup (equivalent to `--profile`). |180| `profile` | `string` | Default profile applied at startup (equivalent to `--profile`). |

141| `profiles.<name>.*` | `various` | Profile-scoped overrides for any of the supported configuration keys. |181| `profiles.<name>.*` | `various` | Profile-scoped overrides for any of the supported configuration keys. |

142| `profiles.<name>.experimental_use_freeform_apply_patch` | `boolean` | Legacy name for enabling freeform apply\_patch; prefer `[features].apply_patch_freeform`. |182| `profiles.<name>.analytics.enabled` | `boolean` | Profile-scoped analytics enablement override. |

143| `profiles.<name>.experimental_use_unified_exec_tool` | `boolean` | Legacy name for enabling unified exec; prefer `[features].unified_exec`. |183| `profiles.<name>.experimental_use_unified_exec_tool` | `boolean` | Legacy name for enabling unified exec; prefer `[features].unified_exec`. |

144| `profiles.<name>.include_apply_patch_tool` | `boolean` | Legacy name for enabling freeform apply\_patch; prefer `[features].apply_patch_freeform`. |

145| `profiles.<name>.model_catalog_json` | `string (path)` | Profile-scoped model catalog JSON path override (applied on startup only; overrides the top-level `model_catalog_json` for that profile). |184| `profiles.<name>.model_catalog_json` | `string (path)` | Profile-scoped model catalog JSON path override (applied on startup only; overrides the top-level `model_catalog_json` for that profile). |

185| `profiles.<name>.model_instructions_file` | `string (path)` | Profile-scoped replacement for the built-in instruction file. |

146| `profiles.<name>.oss_provider` | `lmstudio | ollama` | Profile-scoped OSS provider for `--oss` sessions. |186| `profiles.<name>.oss_provider` | `lmstudio | ollama` | Profile-scoped OSS provider for `--oss` sessions. |

147| `profiles.<name>.personality` | `none | friendly | pragmatic` | Profile-scoped communication style override for supported models. |187| `profiles.<name>.personality` | `none | friendly | pragmatic` | Profile-scoped communication style override for supported models. |

188| `profiles.<name>.plan_mode_reasoning_effort` | `none | minimal | low | medium | high | xhigh` | Profile-scoped Plan-mode reasoning override. |

189| `profiles.<name>.service_tier` | `flex | fast` | Profile-scoped service tier preference for new turns. |

190| `profiles.<name>.tools_view_image` | `boolean` | Enable or disable the `view_image` tool in that profile. |

148| `profiles.<name>.web_search` | `disabled | cached | live` | Profile-scoped web search mode override (default: `"cached"`). |191| `profiles.<name>.web_search` | `disabled | cached | live` | Profile-scoped web search mode override (default: `"cached"`). |

192| `profiles.<name>.windows.sandbox` | `unelevated | elevated` | Profile-scoped Windows sandbox mode override. |

149| `project_doc_fallback_filenames` | `array<string>` | Additional filenames to try when `AGENTS.md` is missing. |193| `project_doc_fallback_filenames` | `array<string>` | Additional filenames to try when `AGENTS.md` is missing. |

150| `project_doc_max_bytes` | `number` | Maximum bytes read from `AGENTS.md` when building project instructions. |194| `project_doc_max_bytes` | `number` | Maximum bytes read from `AGENTS.md` when building project instructions. |

151| `project_root_markers` | `array<string>` | List of project root marker filenames; used when searching parent directories for the project root. |195| `project_root_markers` | `array<string>` | List of project root marker filenames; used when searching parent directories for the project root. |

156| `sandbox_workspace_write.exclude_tmpdir_env_var` | `boolean` | Exclude `$TMPDIR` from writable roots in workspace-write mode. |200| `sandbox_workspace_write.exclude_tmpdir_env_var` | `boolean` | Exclude `$TMPDIR` from writable roots in workspace-write mode. |

157| `sandbox_workspace_write.network_access` | `boolean` | Allow outbound network access inside the workspace-write sandbox. |201| `sandbox_workspace_write.network_access` | `boolean` | Allow outbound network access inside the workspace-write sandbox. |

158| `sandbox_workspace_write.writable_roots` | `array<string>` | Additional writable roots when `sandbox_mode = "workspace-write"`. |202| `sandbox_workspace_write.writable_roots` | `array<string>` | Additional writable roots when `sandbox_mode = "workspace-write"`. |

203| `service_tier` | `flex | fast` | Preferred service tier for new turns. |

159| `shell_environment_policy.exclude` | `array<string>` | Glob patterns for removing environment variables after the defaults. |204| `shell_environment_policy.exclude` | `array<string>` | Glob patterns for removing environment variables after the defaults. |

160| `shell_environment_policy.experimental_use_profile` | `boolean` | Use the user shell profile when spawning subprocesses. |205| `shell_environment_policy.experimental_use_profile` | `boolean` | Use the user shell profile when spawning subprocesses. |

161| `shell_environment_policy.ignore_default_excludes` | `boolean` | Keep variables containing KEY/SECRET/TOKEN before other filters run. |206| `shell_environment_policy.ignore_default_excludes` | `boolean` | Keep variables containing KEY/SECRET/TOKEN before other filters run. |

166| `skills.config` | `array<object>` | Per-skill enablement overrides stored in config.toml. |211| `skills.config` | `array<object>` | Per-skill enablement overrides stored in config.toml. |

167| `skills.config.<index>.enabled` | `boolean` | Enable or disable the referenced skill. |212| `skills.config.<index>.enabled` | `boolean` | Enable or disable the referenced skill. |

168| `skills.config.<index>.path` | `string (path)` | Path to a skill folder containing `SKILL.md`. |213| `skills.config.<index>.path` | `string (path)` | Path to a skill folder containing `SKILL.md`. |

214| `sqlite_home` | `string (path)` | Directory where Codex stores the SQLite-backed state DB used by agent jobs and other resumable runtime state. |

169| `suppress_unstable_features_warning` | `boolean` | Suppress the warning that appears when under-development feature flags are enabled. |215| `suppress_unstable_features_warning` | `boolean` | Suppress the warning that appears when under-development feature flags are enabled. |

170| `tool_output_token_limit` | `number` | Token budget for storing individual tool/function outputs in history. |216| `tool_output_token_limit` | `number` | Token budget for storing individual tool/function outputs in history. |

171| `tools.web_search` | `boolean` | Deprecated legacy toggle for web search; prefer the top-level `web_search` setting. |217| `tool_suggest.discoverables` | `array<table>` | Allow tool suggestions for additional discoverable connectors or plugins. Each entry uses `type = "connector"` or `"plugin"` and an `id`. |

218| `tools.view_image` | `boolean` | Enable the local-image attachment tool `view_image`. |

219| `tools.web_search` | `boolean | { context_size = "low|medium|high", allowed_domains = [string], location = { country, region, city, timezone } }` | Optional web search tool configuration. The legacy boolean form is still accepted, but the object form lets you set search context size, allowed domains, and approximate user location. |

172| `tui` | `table` | TUI-specific options such as enabling inline desktop notifications. |220| `tui` | `table` | TUI-specific options such as enabling inline desktop notifications. |

173| `tui.alternate_screen` | `auto | always | never` | Control alternate screen usage for the TUI (default: auto; auto skips it in Zellij to preserve scrollback). |221| `tui.alternate_screen` | `auto | always | never` | Control alternate screen usage for the TUI (default: auto; auto skips it in Zellij to preserve scrollback). |

174| `tui.animations` | `boolean` | Enable terminal animations (welcome screen, shimmer, spinner) (default: true). |222| `tui.animations` | `boolean` | Enable terminal animations (welcome screen, shimmer, spinner) (default: true). |

223| `tui.model_availability_nux.<model>` | `integer` | Internal startup-tooltip state keyed by model slug. |

175| `tui.notification_method` | `auto | osc9 | bel` | Notification method for unfocused terminal notifications (default: auto). |224| `tui.notification_method` | `auto | osc9 | bel` | Notification method for unfocused terminal notifications (default: auto). |

176| `tui.notifications` | `boolean | array<string>` | Enable TUI notifications; optionally restrict to specific event types. |225| `tui.notifications` | `boolean | array<string>` | Enable TUI notifications; optionally restrict to specific event types. |

177| `tui.show_tooltips` | `boolean` | Show onboarding tooltips in the TUI welcome screen (default: true). |226| `tui.show_tooltips` | `boolean` | Show onboarding tooltips in the TUI welcome screen (default: true). |

178| `tui.status_line` | `array<string> | null` | Ordered list of TUI footer status-line item identifiers. `null` disables the status line. |227| `tui.status_line` | `array<string> | null` | Ordered list of TUI footer status-line item identifiers. `null` disables the status line. |

228| `tui.terminal_title` | `array<string> | null` | Ordered list of terminal window/tab title item identifiers. Defaults to `["spinner", "project"]`; `null` disables title updates. |

229| `tui.theme` | `string` | Syntax-highlighting theme override (kebab-case theme name). |

179| `web_search` | `disabled | cached | live` | Web search mode (default: `"cached"`; cached uses an OpenAI-maintained index and does not fetch live pages; if you use `--yolo` or another full access sandbox setting, it defaults to `"live"`). Use `"live"` to fetch the most recent data from the web, or `"disabled"` to remove the tool. |230| `web_search` | `disabled | cached | live` | Web search mode (default: `"cached"`; cached uses an OpenAI-maintained index and does not fetch live pages; if you use `--yolo` or another full access sandbox setting, it defaults to `"live"`). Use `"live"` to fetch the most recent data from the web, or `"disabled"` to remove the tool. |

180| `windows_wsl_setup_acknowledged` | `boolean` | Track Windows onboarding acknowledgement (Windows only). |231| `windows_wsl_setup_acknowledged` | `boolean` | Track Windows onboarding acknowledgement (Windows only). |

232| `windows.sandbox` | `unelevated | elevated` | Windows-only native sandbox mode when running Codex natively on Windows. |

233| `windows.sandbox_private_desktop` | `boolean` | Run the final sandboxed child process on a private desktop by default on native Windows. Set `false` only for compatibility with the older `Winsta0\\Default` behavior. |

181 234 

182Key235Key

183 236 

205 258 

206Key259Key

207 260 

261`agents.<name>.nickname_candidates`

262 

263Type / Values

264 

265`array<string>`

266 

267Details

268 

269Optional pool of display nicknames for spawned agents in that role.

270 

271Key

272 

273`agents.job_max_runtime_seconds`

274 

275Type / Values

276 

277`number`

278 

279Details

280 

281Default per-worker timeout for `spawn_agents_on_csv` jobs. When unset, the tool falls back to 1800 seconds per worker.

282 

283Key

284 

208`agents.max_depth`285`agents.max_depth`

209 286 

210Type / Values287Type / Values

225 302 

226Details303Details

227 304 

228Maximum number of agent threads that can be open concurrently.305Maximum number of agent threads that can be open concurrently. Defaults to `6` when unset.

229 306 

230Key307Key

231 308 

241 318 

242Key319Key

243 320 

321`analytics.enabled`

322 

323Type / Values

324 

325`boolean`

326 

327Details

328 

329Enable or disable analytics for this machine/profile. When unset, the client default applies.

330 

331Key

332 

244`approval_policy`333`approval_policy`

245 334 

246Type / Values335Type / Values

247 336 

248`untrusted | on-request | never | { reject = { sandbox_approval = bool, rules = bool, mcp_elicitations = bool } }`337`untrusted | on-request | never | { granular = { sandbox_approval = bool, rules = bool, mcp_elicitations = bool, request_permissions = bool, skill_approval = bool } }`

338 

339Details

340 

341Controls when Codex pauses for approval before executing commands. You can also use `approval_policy = { granular = { ... } }` to allow or auto-reject specific prompt categories while keeping other prompts interactive. `on-failure` is deprecated; use `on-request` for interactive runs or `never` for non-interactive runs.

342 

343Key

344 

345`approval_policy.granular.mcp_elicitations`

346 

347Type / Values

348 

349`boolean`

350 

351Details

352 

353When `true`, MCP elicitation prompts are allowed to surface instead of being auto-rejected.

354 

355Key

356 

357`approval_policy.granular.request_permissions`

358 

359Type / Values

360 

361`boolean`

249 362 

250Details363Details

251 364 

252Controls when Codex pauses for approval before executing commands. You can also use `approval_policy = { reject = { ... } }` to auto-reject specific prompt categories while keeping other prompts interactive. `on-failure` is deprecated; use `on-request` for interactive runs or `never` for non-interactive runs.365When `true`, prompts from the `request_permissions` tool are allowed to surface.

253 366 

254Key367Key

255 368 

256`approval_policy.reject.mcp_elicitations`369`approval_policy.granular.rules`

257 370 

258Type / Values371Type / Values

259 372 

261 374 

262Details375Details

263 376 

264When `true`, MCP elicitation prompts are auto-rejected instead of shown to the user.377When `true`, approvals triggered by execpolicy `prompt` rules are allowed to surface.

265 378 

266Key379Key

267 380 

268`approval_policy.reject.rules`381`approval_policy.granular.sandbox_approval`

269 382 

270Type / Values383Type / Values

271 384 

273 386 

274Details387Details

275 388 

276When `true`, approvals triggered by execpolicy `prompt` rules are auto-rejected.389When `true`, sandbox escalation approval prompts are allowed to surface.

277 390 

278Key391Key

279 392 

280`approval_policy.reject.sandbox_approval`393`approval_policy.granular.skill_approval`

281 394 

282Type / Values395Type / Values

283 396 

285 398 

286Details399Details

287 400 

288When `true`, sandbox escalation approval prompts are auto-rejected.401When `true`, skill-script approval prompts are allowed to surface.

402 

403Key

404 

405`approvals_reviewer`

406 

407Type / Values

408 

409`user | guardian_subagent`

410 

411Details

412 

413Select who reviews eligible approval prompts. Defaults to `user`; `guardian_subagent` routes supported reviews through the Guardian reviewer subagent.

289 414 

290Key415Key

291 416 

457 582 

458Key583Key

459 584 

460`compact_prompt`585`commit_attribution`

461 586 

462Type / Values587Type / Values

463 588 

465 590 

466Details591Details

467 592 

468Inline override for the history compaction prompt.593Override the commit co-author trailer text. Set an empty string to disable automatic attribution.

469 594 

470Key595Key

471 596 

472`developer_instructions`597`compact_prompt`

473 598 

474Type / Values599Type / Values

475 600 

477 602 

478Details603Details

479 604 

480Additional developer instructions injected into the session (optional).605Inline override for the history compaction prompt.

481 606 

482Key607Key

483 608 

484`disable_paste_burst`609`default_permissions`

485 610 

486Type / Values611Type / Values

487 612 

488`boolean`613`string`

489 614 

490Details615Details

491 616 

492Disable burst-paste detection in the TUI.617Name of the default permissions profile to apply to sandboxed tool calls.

493 618 

494Key619Key

495 620 

496`experimental_compact_prompt_file`621`developer_instructions`

497 622 

498Type / Values623Type / Values

499 624 

500`string (path)`625`string`

501 626 

502Details627Details

503 628 

504Load the compaction prompt override from a file (experimental).629Additional developer instructions injected into the session (optional).

505 630 

506Key631Key

507 632 

508`experimental_use_freeform_apply_patch`633`disable_paste_burst`

509 634 

510Type / Values635Type / Values

511 636 

513 638 

514Details639Details

515 640 

516Legacy name for enabling freeform apply\_patch; prefer `[features].apply_patch_freeform` or `codex --enable apply_patch_freeform`.641Disable burst-paste detection in the TUI.

517 642 

518Key643Key

519 644 

520`experimental_use_unified_exec_tool`645`experimental_compact_prompt_file`

521 646 

522Type / Values647Type / Values

523 648 

524`boolean`649`string (path)`

525 650 

526Details651Details

527 652 

528Legacy name for enabling unified exec; prefer `[features].unified_exec` or `codex --enable unified_exec`.653Load the compaction prompt override from a file (experimental).

529 654 

530Key655Key

531 656 

532`features.apply_patch_freeform`657`experimental_use_unified_exec_tool`

533 658 

534Type / Values659Type / Values

535 660 

537 662 

538Details663Details

539 664 

540Expose the freeform `apply_patch` tool (experimental).665Legacy name for enabling unified exec; prefer `[features].unified_exec` or `codex --enable unified_exec`.

541 666 

542Key667Key

543 668 

553 678 

554Key679Key

555 680 

556`features.apps_mcp_gateway`681`features.codex_hooks`

557 

558Type / Values

559 

560`boolean`

561 

562Details

563 

564Route Apps MCP calls through the OpenAI connectors MCP gateway (`https://api.openai.com/v1/connectors/mcp/`) instead of legacy routing (experimental).

565 

566Key

567 

568`features.child_agents_md`

569 682 

570Type / Values683Type / Values

571 684 

573 686 

574Details687Details

575 688 

576Append AGENTS.md scope/precedence guidance even when no AGENTS.md is present (experimental).689Enable lifecycle hooks loaded from `hooks.json` (under development; off by default).

577 690 

578Key691Key

579 692 

580`features.collaboration_modes`693`features.enable_request_compression`

581 694 

582Type / Values695Type / Values

583 696 

585 698 

586Details699Details

587 700 

588Enable collaboration modes such as plan mode (stable; on by default).701Compress streaming request bodies with zstd when supported (stable; on by default).

589 702 

590Key703Key

591 704 

592`features.elevated_windows_sandbox`705`features.fast_mode`

593 706 

594Type / Values707Type / Values

595 708 

597 710 

598Details711Details

599 712 

600Enable the elevated Windows sandbox pipeline (experimental).713Enable Fast mode selection and the `service_tier = "fast"` path (stable; on by default).

601 714 

602Key715Key

603 716 

604`features.experimental_windows_sandbox`717`features.memories`

605 718 

606Type / Values719Type / Values

607 720 

609 722 

610Details723Details

611 724 

612Run the Windows restricted-token sandbox (experimental).725Enable [Memories](https://developers.openai.com/codex/memories) (off by default).

613 726 

614Key727Key

615 728 

621 734 

622Details735Details

623 736 

624Enable multi-agent collaboration tools (`spawn\_agent`, `send\_input`, `resume\_agent`, `wait`, and `close\_agent`) (experimental; off by default).737Enable multi-agent collaboration tools (`spawn_agent`, `send_input`, `resume_agent`, `wait_agent`, and `close_agent`) (stable; on by default).

625 738 

626Key739Key

627 740 

637 750 

638Key751Key

639 752 

640`features.powershell_utf8`753`features.prevent_idle_sleep`

641 

642Type / Values

643 

644`boolean`

645 

646Details

647 

648Force PowerShell UTF-8 output (defaults to true).

649 

650Key

651 

652`features.remote_models`

653 754 

654Type / Values755Type / Values

655 756 

657 758 

658Details759Details

659 760 

660Refresh remote model list before showing readiness (experimental).761Prevent the machine from sleeping while a turn is actively running (experimental; off by default).

661 762 

662Key763Key

663 764 

664`features.request_rule`765`features.shell_snapshot`

665 766 

666Type / Values767Type / Values

667 768 

669 770 

670Details771Details

671 772 

672Enable Smart approvals (`prefix_rule` suggestions on escalation requests; stable; on by default).773Snapshot shell environment to speed up repeated commands (stable; on by default).

673 774 

674Key775Key

675 776 

676`features.runtime_metrics`777`features.shell_tool`

677 778 

678Type / Values779Type / Values

679 780 

681 782 

682Details783Details

683 784 

684Show runtime metrics summary in TUI turn separators (experimental).785Enable the default `shell` tool for running commands (stable; on by default).

685 786 

686Key787Key

687 788 

688`features.search_tool`789`features.skill_mcp_dependency_install`

689 790 

690Type / Values791Type / Values

691 792 

693 794 

694Details795Details

695 796 

696Enable `search_tool_bm25` for Apps tool discovery before invoking app MCP tools (experimental).797Allow prompting and installing missing MCP dependencies for skills (stable; on by default).

697 798 

698Key799Key

699 800 

700`features.shell_snapshot`801`features.smart_approvals`

701 802 

702Type / Values803Type / Values

703 804 

705 806 

706Details807Details

707 808 

708Snapshot shell environment to speed up repeated commands (beta).809Route eligible approval requests through the guardian reviewer subagent (experimental; off by default).

709 810 

710Key811Key

711 812 

712`features.shell_tool`813`features.undo`

713 814 

714Type / Values815Type / Values

715 816 

717 818 

718Details819Details

719 820 

720Enable the default `shell` tool for running commands (stable; on by default).821Enable undo support (stable; off by default).

721 822 

722Key823Key

723 824 

729 830 

730Details831Details

731 832 

732Use the unified PTY-backed exec tool (beta).833Use the unified PTY-backed exec tool (stable; enabled by default except on Windows).

733 

734Key

735 

736`features.use_linux_sandbox_bwrap`

737 

738Type / Values

739 

740`boolean`

741 

742Details

743 

744Use the bubblewrap-based Linux sandbox pipeline (experimental; off by default).

745 834 

746Key835Key

747 836 

865 954 

866Key955Key

867 956 

868`include_apply_patch_tool`

869 

870Type / Values

871 

872`boolean`

873 

874Details

875 

876Legacy name for enabling freeform apply\_patch; prefer `[features].apply_patch_freeform`.

877 

878Key

879 

880`instructions`957`instructions`

881 958 

882Type / Values959Type / Values

1069 1146 

1070Key1147Key

1071 1148 

1149`mcp_servers.<id>.oauth_resource`

1150 

1151Type / Values

1152 

1153`string`

1154 

1155Details

1156 

1157Optional RFC 8707 OAuth resource parameter to include during MCP login.

1158 

1159Key

1160 

1072`mcp_servers.<id>.required`1161`mcp_servers.<id>.required`

1073 1162 

1074Type / Values1163Type / Values

1081 1170 

1082Key1171Key

1083 1172 

1173`mcp_servers.<id>.scopes`

1174 

1175Type / Values

1176 

1177`array<string>`

1178 

1179Details

1180 

1181OAuth scopes to request when authenticating to that MCP server.

1182 

1183Key

1184 

1084`mcp_servers.<id>.startup_timeout_ms`1185`mcp_servers.<id>.startup_timeout_ms`

1085 1186 

1086Type / Values1187Type / Values

1129 1230 

1130Key1231Key

1131 1232 

1132`model`1233`memories.consolidation_model`

1133 1234 

1134Type / Values1235Type / Values

1135 1236 

1137 1238 

1138Details1239Details

1139 1240 

1140Model to use (e.g., `gpt-5-codex`).1241Optional model override for global memory consolidation.

1141 1242 

1142Key1243Key

1143 1244 

1144`model_auto_compact_token_limit`1245`memories.extract_model`

1145 1246 

1146Type / Values1247Type / Values

1147 1248 

1148`number`1249`string`

1149 1250 

1150Details1251Details

1151 1252 

1152Token threshold that triggers automatic history compaction (unset uses model defaults).1253Optional model override for per-thread memory extraction.

1153 1254 

1154Key1255Key

1155 1256 

1156`model_catalog_json`1257`memories.generate_memories`

1157 1258 

1158Type / Values1259Type / Values

1159 1260 

1160`string (path)`1261`boolean`

1161 1262 

1162Details1263Details

1163 1264 

1164Optional path to a JSON model catalog loaded on startup. Profile-level `profiles.<name>.model_catalog_json` can override this per profile.1265When `false`, newly created threads are not stored as memory-generation inputs. Defaults to `true`.

1165 1266 

1166Key1267Key

1167 1268 

1168`model_context_window`1269`memories.max_raw_memories_for_consolidation`

1169 1270 

1170Type / Values1271Type / Values

1171 1272 

1173 1274 

1174Details1275Details

1175 1276 

1176Context window tokens available to the active model.1277Maximum recent raw memories retained for global consolidation. Defaults to `256` and is capped at `4096`.

1177 1278 

1178Key1279Key

1179 1280 

1180`model_instructions_file`1281`memories.max_rollout_age_days`

1181 1282 

1182Type / Values1283Type / Values

1183 1284 

1184`string (path)`1285`number`

1185 1286 

1186Details1287Details

1187 1288 

1188Replacement for built-in instructions instead of `AGENTS.md`.1289Maximum age of threads considered for memory generation. Defaults to `30` and is clamped to `0`-`90`.

1189 1290 

1190Key1291Key

1191 1292 

1192`model_provider`1293`memories.max_rollouts_per_startup`

1193 1294 

1194Type / Values1295Type / Values

1195 1296 

1196`string`1297`number`

1197 1298 

1198Details1299Details

1199 1300 

1200Provider id from `model_providers` (default: `openai`).1301Maximum rollout candidates processed per startup pass. Defaults to `16` and is capped at `128`.

1201 1302 

1202Key1303Key

1203 1304 

1204`model_providers.<id>.base_url`1305`memories.max_unused_days`

1205 1306 

1206Type / Values1307Type / Values

1207 1308 

1208`string`1309`number`

1209 1310 

1210Details1311Details

1211 1312 

1212API base URL for the model provider.1313Maximum days since a memory was last used before it becomes ineligible for consolidation. Defaults to `30` and is clamped to `0`-`365`.

1213 1314 

1214Key1315Key

1215 1316 

1216`model_providers.<id>.env_http_headers`1317`memories.min_rollout_idle_hours`

1217 1318 

1218Type / Values1319Type / Values

1219 1320 

1220`map<string,string>`1321`number`

1221 1322 

1222Details1323Details

1223 1324 

1224HTTP headers populated from environment variables when present.1325Minimum idle time before a thread is considered for memory generation. Defaults to `6` and is clamped to `1`-`48`.

1225 1326 

1226Key1327Key

1227 1328 

1228`model_providers.<id>.env_key`1329`memories.no_memories_if_mcp_or_web_search`

1229 1330 

1230Type / Values1331Type / Values

1231 1332 

1232`string`1333`boolean`

1233 1334 

1234Details1335Details

1235 1336 

1236Environment variable supplying the provider API key.1337When `true`, threads that use MCP tool calls or web search are kept out of memory generation. Defaults to `false`.

1237 1338 

1238Key1339Key

1239 1340 

1240`model_providers.<id>.env_key_instructions`1341`memories.use_memories`

1241 1342 

1242Type / Values1343Type / Values

1243 1344 

1244`string`1345`boolean`

1245 1346 

1246Details1347Details

1247 1348 

1248Optional setup guidance for the provider API key.1349When `false`, Codex skips injecting existing memories into future sessions. Defaults to `true`.

1249 1350 

1250Key1351Key

1251 1352 

1252`model_providers.<id>.experimental_bearer_token`1353`model`

1253 1354 

1254Type / Values1355Type / Values

1255 1356 

1257 1358 

1258Details1359Details

1259 1360 

1260Direct bearer token for the provider (discouraged; use `env_key`).1361Model to use (e.g., `gpt-5.4`).

1261 1362 

1262Key1363Key

1263 1364 

1264`model_providers.<id>.http_headers`1365`model_auto_compact_token_limit`

1265 1366 

1266Type / Values1367Type / Values

1267 1368 

1268`map<string,string>`1369`number`

1269 1370 

1270Details1371Details

1271 1372 

1272Static HTTP headers added to provider requests.1373Token threshold that triggers automatic history compaction (unset uses model defaults).

1273 1374 

1274Key1375Key

1275 1376 

1276`model_providers.<id>.name`1377`model_catalog_json`

1277 1378 

1278Type / Values1379Type / Values

1279 1380 

1280`string`1381`string (path)`

1281 1382 

1282Details1383Details

1283 1384 

1284Display name for a custom model provider.1385Optional path to a JSON model catalog loaded on startup. Profile-level `profiles.<name>.model_catalog_json` can override this per profile.

1285 1386 

1286Key1387Key

1287 1388 

1288`model_providers.<id>.query_params`1389`model_context_window`

1289 1390 

1290Type / Values1391Type / Values

1291 1392 

1292`map<string,string>`1393`number`

1293 1394 

1294Details1395Details

1295 1396 

1296Extra query parameters appended to provider requests.1397Context window tokens available to the active model.

1297 1398 

1298Key1399Key

1299 1400 

1300`model_providers.<id>.request_max_retries`1401`model_instructions_file`

1301 1402 

1302Type / Values1403Type / Values

1303 1404 

1304`number`1405`string (path)`

1305 1406 

1306Details1407Details

1307 1408 

1308Retry count for HTTP requests to the provider (default: 4).1409Replacement for built-in instructions instead of `AGENTS.md`.

1309 1410 

1310Key1411Key

1311 1412 

1312`model_providers.<id>.requires_openai_auth`1413`model_provider`

1313 1414 

1314Type / Values1415Type / Values

1315 1416 

1316`boolean`1417`string`

1317 1418 

1318Details1419Details

1319 1420 

1320The provider uses OpenAI authentication (defaults to false).1421Provider id from `model_providers` (default: `openai`).

1321 1422 

1322Key1423Key

1323 1424 

1324`model_providers.<id>.stream_idle_timeout_ms`1425`model_providers.<id>`

1325 1426 

1326Type / Values1427Type / Values

1327 1428 

1328`number`1429`table`

1329 1430 

1330Details1431Details

1331 1432 

1332Idle timeout for SSE streams in milliseconds (default: 300000).1433Custom provider definition. Built-in provider IDs (`openai`, `ollama`, and `lmstudio`) are reserved and cannot be overridden.

1333 1434 

1334Key1435Key

1335 1436 

1336`model_providers.<id>.stream_max_retries`1437`model_providers.<id>.auth`

1337 1438 

1338Type / Values1439Type / Values

1339 1440 

1340`number`1441`table`

1341 1442 

1342Details1443Details

1343 1444 

1344Retry count for SSE streaming interruptions (default: 5).1445Command-backed bearer token configuration for a custom provider. Do not combine with `env_key`, `experimental_bearer_token`, or `requires_openai_auth`.

1345 1446 

1346Key1447Key

1347 1448 

1348`model_providers.<id>.wire_api`1449`model_providers.<id>.auth.args`

1349 1450 

1350Type / Values1451Type / Values

1351 1452 

1352`chat | responses`1453`array<string>`

1353 1454 

1354Details1455Details

1355 1456 

1356Protocol used by the provider (defaults to `chat` if omitted).1457Arguments passed to the token command.

1357 1458 

1358Key1459Key

1359 1460 

1360`model_reasoning_effort`1461`model_providers.<id>.auth.command`

1361 1462 

1362Type / Values1463Type / Values

1363 1464 

1364`minimal | low | medium | high | xhigh`1465`string`

1365 1466 

1366Details1467Details

1367 1468 

1368Adjust reasoning effort for supported models (Responses API only; `xhigh` is model-dependent).1469Command to run when Codex needs a bearer token. The command must print the token to stdout.

1369 1470 

1370Key1471Key

1371 1472 

1372`model_reasoning_summary`1473`model_providers.<id>.auth.cwd`

1373 1474 

1374Type / Values1475Type / Values

1375 1476 

1376`auto | concise | detailed | none`1477`string (path)`

1377 1478 

1378Details1479Details

1379 1480 

1380Select reasoning summary detail or disable summaries entirely.1481Working directory for the token command.

1381 1482 

1382Key1483Key

1383 1484 

1384`model_supports_reasoning_summaries`1485`model_providers.<id>.auth.refresh_interval_ms`

1385 1486 

1386Type / Values1487Type / Values

1387 1488 

1388`boolean`1489`number`

1389 1490 

1390Details1491Details

1391 1492 

1392Force Codex to send or not send reasoning metadata.1493How often Codex proactively refreshes the token in milliseconds (default: 300000). Set to `0` to refresh only after an authentication retry.

1393 1494 

1394Key1495Key

1395 1496 

1396`model_verbosity`1497`model_providers.<id>.auth.timeout_ms`

1397 1498 

1398Type / Values1499Type / Values

1399 1500 

1400`low | medium | high`1501`number`

1401 1502 

1402Details1503Details

1403 1504 

1404Control GPT-5 Responses API verbosity (defaults to `medium`).1505Maximum token command runtime in milliseconds (default: 5000).

1405 1506 

1406Key1507Key

1407 1508 

1408`notice.hide_full_access_warning`1509`model_providers.<id>.base_url`

1409 1510 

1410Type / Values1511Type / Values

1411 1512 

1412`boolean`1513`string`

1413 1514 

1414Details1515Details

1415 1516 

1416Track acknowledgement of the full access warning prompt.1517API base URL for the model provider.

1417 1518 

1418Key1519Key

1419 1520 

1420`notice.hide_gpt-5.1-codex-max_migration_prompt`1521`model_providers.<id>.env_http_headers`

1421 1522 

1422Type / Values1523Type / Values

1423 1524 

1424`boolean`1525`map<string,string>`

1425 1526 

1426Details1527Details

1427 1528 

1428Track acknowledgement of the gpt-5.1-codex-max migration prompt.1529HTTP headers populated from environment variables when present.

1530 

1531Key

1532 

1533`model_providers.<id>.env_key`

1534 

1535Type / Values

1536 

1537`string`

1538 

1539Details

1540 

1541Environment variable supplying the provider API key.

1542 

1543Key

1544 

1545`model_providers.<id>.env_key_instructions`

1546 

1547Type / Values

1548 

1549`string`

1550 

1551Details

1552 

1553Optional setup guidance for the provider API key.

1554 

1555Key

1556 

1557`model_providers.<id>.experimental_bearer_token`

1558 

1559Type / Values

1560 

1561`string`

1562 

1563Details

1564 

1565Direct bearer token for the provider (discouraged; use `env_key`).

1566 

1567Key

1568 

1569`model_providers.<id>.http_headers`

1570 

1571Type / Values

1572 

1573`map<string,string>`

1574 

1575Details

1576 

1577Static HTTP headers added to provider requests.

1578 

1579Key

1580 

1581`model_providers.<id>.name`

1582 

1583Type / Values

1584 

1585`string`

1586 

1587Details

1588 

1589Display name for a custom model provider.

1590 

1591Key

1592 

1593`model_providers.<id>.query_params`

1594 

1595Type / Values

1596 

1597`map<string,string>`

1598 

1599Details

1600 

1601Extra query parameters appended to provider requests.

1602 

1603Key

1604 

1605`model_providers.<id>.request_max_retries`

1606 

1607Type / Values

1608 

1609`number`

1610 

1611Details

1612 

1613Retry count for HTTP requests to the provider (default: 4).

1614 

1615Key

1616 

1617`model_providers.<id>.requires_openai_auth`

1618 

1619Type / Values

1620 

1621`boolean`

1622 

1623Details

1624 

1625The provider uses OpenAI authentication (defaults to false).

1626 

1627Key

1628 

1629`model_providers.<id>.stream_idle_timeout_ms`

1630 

1631Type / Values

1632 

1633`number`

1634 

1635Details

1636 

1637Idle timeout for SSE streams in milliseconds (default: 300000).

1638 

1639Key

1640 

1641`model_providers.<id>.stream_max_retries`

1642 

1643Type / Values

1644 

1645`number`

1646 

1647Details

1648 

1649Retry count for SSE streaming interruptions (default: 5).

1650 

1651Key

1652 

1653`model_providers.<id>.supports_websockets`

1654 

1655Type / Values

1656 

1657`boolean`

1658 

1659Details

1660 

1661Whether that provider supports the Responses API WebSocket transport.

1662 

1663Key

1664 

1665`model_providers.<id>.wire_api`

1666 

1667Type / Values

1668 

1669`responses`

1670 

1671Details

1672 

1673Protocol used by the provider. `responses` is the only supported value, and it is the default when omitted.

1674 

1675Key

1676 

1677`model_reasoning_effort`

1678 

1679Type / Values

1680 

1681`minimal | low | medium | high | xhigh`

1682 

1683Details

1684 

1685Adjust reasoning effort for supported models (Responses API only; `xhigh` is model-dependent).

1686 

1687Key

1688 

1689`model_reasoning_summary`

1690 

1691Type / Values

1692 

1693`auto | concise | detailed | none`

1694 

1695Details

1696 

1697Select reasoning summary detail or disable summaries entirely.

1698 

1699Key

1700 

1701`model_supports_reasoning_summaries`

1702 

1703Type / Values

1704 

1705`boolean`

1706 

1707Details

1708 

1709Force Codex to send or not send reasoning metadata.

1710 

1711Key

1712 

1713`model_verbosity`

1714 

1715Type / Values

1716 

1717`low | medium | high`

1718 

1719Details

1720 

1721Optional GPT-5 Responses API verbosity override; when unset, the selected model/preset default is used.

1722 

1723Key

1724 

1725`notice.hide_full_access_warning`

1726 

1727Type / Values

1728 

1729`boolean`

1730 

1731Details

1732 

1733Track acknowledgement of the full access warning prompt.

1734 

1735Key

1736 

1737`notice.hide_gpt-5.1-codex-max_migration_prompt`

1738 

1739Type / Values

1740 

1741`boolean`

1742 

1743Details

1744 

1745Track acknowledgement of the gpt-5.1-codex-max migration prompt.

1429 1746 

1430Key1747Key

1431 1748